2022-06-28-idrissi22a.md

abstract	booktitle	title	year	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
We study the problem of learning classifiers that perform well across (known or unknown) groups of data. After observing that common worst-group-accuracy datasets suffer from substantial imbalances, we set out to compare state-of-the-art methods to simple balancing of classes and groups by either subsampling or reweighting data. Our results show that these data balancing baselines achieve state-of-the-art-accuracy, while being faster to train and requiring no additional hyper-parameters. Finally, we highlight that access to group information is most critical for model selection purposes, and not so much during training. All in all, our findings beg closer examination of both benchmarks and methods for future research in worst-group-accuracy optimization.	First Conference on Causal Learning and Reasoning	Simple data balancing achieves competitive worst-group-accuracy	2022	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	idrissi22a	0	Simple data balancing achieves competitive worst-group-accuracy	336	351	336-351	336	false	Idrissi, Badr Youbi and Arjovsky, Martin and Pezeshki, Mohammad and Lopez-Paz, David	given family Badr Youbi Idrissi given family Martin Arjovsky given family Mohammad Pezeshki given family David Lopez-Paz	2022-06-28		Proceedings of the First Conference on Causal Learning and Reasoning	177	inproceedings	date-parts 2022 6 28	https://proceedings.mlr.press/v177/idrissi22a/idrissi22a.pdf